GlobalNER: Incorporating Non-local Information into Named Entity Recognition
Computation and Language
2023-03-07 v1 Artificial Intelligence
Abstract
Nowadays, many Natural Language Processing (NLP) tasks see the demand for incorporating knowledge external to the local information to further improve the performance. However, there is little related work on Named Entity Recognition (NER), which is one of the foundations of NLP. Specifically, no studies were conducted on the query generation and re-ranking for retrieving the related information for the purpose of improving NER. This work demonstrates the effectiveness of a DNN-based query generation method and a mention-aware re-ranking architecture based on BERTScore particularly for NER. In the end, a state-of-the-art performance of 61.56 micro-f1 score on WNUT17 dataset is achieved.
Cite
@article{arxiv.2303.02915,
title = {GlobalNER: Incorporating Non-local Information into Named Entity Recognition},
author = {Chiao-Wei Hsu and Keh-Yih Su},
journal= {arXiv preprint arXiv:2303.02915},
year = {2023}
}
Comments
13 pages, 5 figures